Kernel Learning Algorithms for Face Recognition
Jun-Bao Li, Shu-Chuan Chu, Jeng-Shyang Pan
Format: PDF / Kindle (mobi) / ePub
Kernel Learning Algorithms for Face Recognition covers the framework of kernel based face recognition. This book discusses the advanced kernel learning algorithms and its application on face recognition. This book also focuses on the theoretical deviation, the system framework and experiments involving kernel based face recognition. Included within are algorithms of kernel based face recognition, and also the feasibility of the kernel based face recognition method. This book provides researchers in pattern recognition and machine learning area with advanced face recognition methods and its newest applications.
Ratsch G, Tsuda K, Scholkopf B (2001) An introduction to kernelbased learning algorithms. IEEE Trans Neural Networks 12(2):181–201 33. Campbell C (2002) Kernel methods: a survey of current techniques. Neurocomputing 48:63–84 34. Ruiz A, Lopez-de-Teruel PE (2001) Nonlinear Kernel-based statistical pattern analysis. IEEE Trans Neural Networks 12(1):1045–1052 35. Mika S, Ratsch G, Weston J, Scholkopf B, Muller K (1999) Fisher discriminant analysis with kernels. IEEE neural networks for signal
recognition method, principal component analysis (PCA) has been widely studied. Some recent advances in PCA-based algorithms include weighted modular PCA , adaptively weighted subpattern PCA , twodimensional PCA [10, 11], multi-linear subspace analysis , eigenbands , symmetrical PCA . 2.2.2 Video-Based Face Recognition With the development of video surveillance, video-based face recognition has widely used in many areas. Video-based face recognition system typically consists of
Advances in Kernel methods, support vector learning. MIT Press, Cambridge 13. Saha B, Goebel K, Poll S, Christophersen J (2007) An integrated approach to battery health monitoring using Bayesian regression and state estimation. In: Proceedings of autotestcon, pp 646–653 14. Zio E, Di Maio F (2010) A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system. Reliab Eng Syst Saf 95:49–57 15. Luo M, Wang D, Pham M, Low CB, Zhang JB, Zhang
ðxli ; j; kÞÞ ð5:58Þ where dðv1 ; v2 Þ is the Euclidean distance between two vector v1 andv2 ; and a is the a parameter ranging from zero to infinity which the changing of the weight À l control Á with respect to the ratio of the distance. N xi ; j; k is the kth nearest neighbor from class j to the vector xli which from lth sample of ith class. Algorithm Procedure: À Á Step 1. Calculate kth nearest neighbor vector N xli ; j; k from class j to the vector xli which from lth sample of ith class.
method. As shown in Tables 7.1 and 7.2, SGGLPP outperforms other algorithms for the same training and test sets. Although the recognition rate is not high, it indicates that it is feasible to improve the performance with unlabeled classes together with the side information. Moreover, semi-supervised learning methods perform better than the unsupervised learning methods; for example, SLPP outperforms LPP. SGGLPP integrates graph construction with specific SGGLPP-based DR process into a unified